training_stats.json

{
  "phase": "Phase 3 - Formulator",
  "base_model": "Qwen/Qwen2.5-7B-Instruct",
  "dataset": "/home/beta1/gt-training/formulator/formulator_dataset.json",
  "dataset_size": 1215,
  "train_examples": 1093,
  "eval_examples": 122,
  "lora_r": 32,
  "lora_alpha": 64,
  "target_modules": "all_linear",
  "epochs": 1,
  "batch_size_per_device": 2,
  "grad_accum": 4,
  "effective_batch": 16,
  "learning_rate": 5e-05,
  "lr_scheduler": "cosine",
  "max_seq_length": 2048,
  "quantization": "4bit_nf4",
  "train_loss": 1.0992090911195989,
  "eval_loss": 0.8491532206535339,
  "runtime_seconds": 1458.7688,
  "runtime_minutes": 24.312813333333334,
  "total_wall_time_seconds": 1469.986917257309,
  "samples_per_second": 0.311,
  "num_gpus": 2
}